ValueError:`decode_predictions`需要一批预测(即2D形状的数组(样本，1000个)).找到形状为(1，7)的数组 [英] ValueError: `decode_predictions` expects a batch of predictions (i.e. a 2D array of shape (samples, 1000)). Found array with shape: (1, 7)

问题描述

我正在将VGG16与keras一起用于迁移学习(我的新模型中有7个类)，因此，我想使用内置的encode_predictions方法输出我的模型的预测.但是，使用以下代码:

I am using VGG16 with keras for transfer learning (I have 7 classes in my new model) and as such I want to use the build-in decode_predictions method to output the predictions of my model. However, using the following code:

preds = model.predict(img)

decode_predictions(preds, top=3)[0]

我收到以下错误消息:

ValueError:decode_predictions期望进行一系列预测(即2D形状的数组(样本，1000个)).找到形状为(1，7)

ValueError: decode_predictions expects a batch of predictions (i.e. a 2D array of shape (samples, 1000)). Found array with shape: (1, 7)

现在，我想知道为什么在重新训练的模型中只有7个类时会期望1000.

Now I wonder why it expects 1000 when I only have 7 classes in my retrained model.

我在stackoverflow上发现了一个类似的问题( Keras: ValueError:decode_predictions需要一批预测 )建议在模型定义中包含"inlcude_top = True"以解决此问题:

A similar question I found here on stackoverflow (Keras: ValueError: decode_predictions expects a batch of predictions ) suggests to include 'inlcude_top=True' upon model definition to solve this problem:

model = VGG16(weights='imagenet', include_top=True)

我已经尝试过了，但是仍然无法正常工作-给我和以前一样的错误.对于如何解决此问题的任何提示或建议，我们深表感谢.

I have tried this, however it is still not working - giving me the same error as before. Any hint or suggestion on how to solve this issue is highly appreciated.

推荐答案

我怀疑您使用的是预先训练的模型，例如说resnet50，并且您正在导入decode_predictions，如下所示:

i suspect you are using some pre-trained model, let's say for instance resnet50 and you are importing decode_predictions like this:

from keras.applications.resnet50 import decode_predictions

decode_predictions将(num_samples，1000)个概率数组转换为原始imagenet类的类名.

decode_predictions transform an array of (num_samples, 1000) probabilities to class name of original imagenet classes.

如果您想在7个不同的班级之间进行学习和分类，您需要这样做:

if you want to transer learning and classify between 7 different classes you need to do it like this:

base_model = resnet50 (weights='imagenet', include_top=False)

# add a global spatial average pooling layer
x = base_model.output
x = GlobalAveragePooling2D()(x)
# add a fully-connected layer
x = Dense(1024, activation='relu')(x)
# and a logistic layer -- let's say we have 7 classes
predictions = Dense(7, activation='softmax')(x) 
model = Model(inputs=base_model.input, outputs=predictions)
...

在拟合模型并计算预测之后，您必须使用导入的decode_predictions

after fitting the model and calculate predictions you have to manually assign the class name to output number without using imported decode_predictions

这篇关于ValueError:`decode_predictions`需要一批预测(即2D形状的数组(样本，1000个)).找到形状为(1，7)的数组的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！